C4.5 Classifier for Solving the Problem of Water Resources Engineering

Abstract

The conventional decision-tree algorithm, such as ID3 and C5.0, executes rapidly and can easily be translated into if-thenelse rules.  This paper introduces popular classifier C4.5 for dealing with water resources engineering  problem. The  proposed approach was applied to the Shihmen Reservoir, which is one of the largest reservoirs, located upstream of the Tahan River Basin of northern Taiwan. The existing rules, namely M5-C rules, include two main flood stages: the peak-flow-preceding stage and the peakflow-proceeding stage. The findings show superior performance of the C4.5 rules in contrast to M5-C rules. Accordingly, C4.5 rules can be used to improve the engineering problem.